Tensorflow：來自Tensorflow中Caffe的weight_filler「gaussian」的等價物是什麼？

Question

我試圖將Caffemodel轉換爲tensorflow。在caffe我的卷積初始化是這樣的：

weight_filler { 
    type: "gaussian" 
    std: 0.01 
} 
bias_filler { 
    type: "constant" 
    value: 0 
} 

如何在Tensorflow中獲得相同的初始化？

Answer 1

隨着tf.truncated_normal您可以從截斷隨機分佈得到隨機值，即：

shape = [10,10] # variable shape 
weight = tf.Variable(tf.truncated_normal(shape, mean=0.0, stddev=0.01)) 
bias = tf.Variable(0.)